Participants of former LTC events came from:

Since 1995! 22nd Anniversary!

Patronage:

Dear Colleagues,

The 8th Language and Technology Conference (LTC 2017), a meeting organized by the Faculty of Mathematics and Computer Science of the Adam Mickiewicz University, Poznań, Poland and the Adam Mickiewicz University Foundation, will take place on November 17-19, 2017. Following the tradition of the past events, it is supported by ELRA, FlaReNet, and META-NET.

Yes, we started 22 years ago! Our tradition goes back to the Language and Technology Awareness Days, a meeting organized in 1995 with the assistance of the European Commission (DG XIII). Among the key speakers were Antonio Zampolli (Italy), Dafydd Gibbon (Germany), Dan Tufiş (Romania), Orest Kossak (Ukraina). Today, we refer to this event as the first LTC. Ten years later, we decided to meet again, and since then the conference is being organized every two years as the “Language & Technology Conference: Human Language Technologies as a Challenge for Computer Science and Linguistics”.

Since the very beginning (1995) the meetings of the LTC series continue to address Human Language Technologies (HLT) as a challenge for computer science, linguistics and related fields. Fostering language technologies and resources remains an important objective in our dynamically changing information-saturated world that motivate us to invite you for joining us at the LTC 2017 in Poznań.

Zygmunt Vetulani and Patrick Paroubek
LTC 2017 Co-Chairs
vetulani@amu.edu.pl and pap@limsi.fr

Chris Cieri

Executive Director, Linguistic Data Consortium,University of Pennsylvania,3600 Market Street, Philadelphia, PA. 19104 Penn State University, USA

BIO: Christopher Cieri’s interests lie at the intersection of language, large data, and computation. He received his PhD in Linguistics from the University of Pennsylvania where he focused on sociolinguistics, language contact, phonetics, phonology and morphology. He has worked since 1983 applying technology to linguistic analysis and language teaching using data sets that are too large to process with purely human effort. Cieri became the Executive Director of the Linguistic Data Consortium in 1998 and has since been responsible for overseeing all aspects of the Consortium’s operations including the publication of over 500 data sets and the management of many sponsored programs. His current work focuses on the science of linguistic annotation and the analysis of conversational data, most recently in identifying linguistic features to correlate with clinical diagnostic categories. See here for CV

Title: Addressing the Language Resource Gap through Alternative Incentives, Workforces and Workflows

Abstract:For most languages, genres and technologies, the absence of Language Resources impedes progress despite several decades of intensive effort from governments and companies around the world. This deficiency even affects languages with worldwide economic and political influence and for most of the world’s 7000 linguistic varieties, the absence is acute. Current approaches cannot hope to meet the resource demand for even a reasonable subset of languages because they seek to document phenomena of great variability using resources that are highly constrained in terms of amount, duration and scope. This paper describes efforts that use non-monetary incentives to elicit greater contributions of linguistic data, metadata and annotation and sketches the adjustments to workforces, workflows and post-processing needed to collect and exploit data so elicited. MORE

Joseph van Genabith

DFKI GmbH, Saarbrücken, Germany

BIO: Josef van Genabith is one of the Scientific Directors of DFKI, the German Research Centre for Artificial Intelligence, where he heads the Multilingual Technologies (MLT) Group, and jointly with Prof. Hans Uszkoreit, the Language Technology (LT) Lab. He is also Professor of Translation-Oriented Language Technologies at Saarland University, Germany. He was the founding Director of the Centre for Next Generation Localisation (CNGL, now ADAPT), in Dublin, Ireland, and a Professor in the School of Computing at Dublin City University (DCU). He worked as a researcher at the Institut für Maschinelle Sprachverarbeitung (IMS) at the University of Stuttgart, Germany. He was awarded a PhD from the University of Essex, U.K., and obtained his first degree at RWTH Aachen, Germany. His research interests include machine translation, parsing, generation, computer-assisted-language-learning and morphology. Currently he coordinates the QT21 H2020 research and innovation project on machine translation (http://www.qt21.eu/) and heads EC SMART 2014/1074 and 2015/1091 service contracts on European Language Resource Coordination (ELRC) (http://www.lr-coordination.eu/). The Impact of Neural Networks on Language Technologies: a Case Study on Machine Translation. MORE

Title: The Impact of Neural Networks on Language Technologies: a Case Study on Machine Translation

Abstract: Deep Neural Nets (DNNs) are revolutionising many (if not most) areas in Artificial Intelligence, including Language Technologies (LTs), often with remarkable performance improvements. In this talk, I would like to take a closer look at why this is the case, focusing on Machine Translation (MT). I will contrast neural MT with previous approaches to MT. In doing so I will be drawing on research carried out in the QT21 H2020 research and innovation project (http://www.qt21.eu/) and QT21 systems for the WMT-2015, -2016 and -2017 shared tasks. I will concentrate on morphologically complex languages with less constrained word order. I will also consider the more general impact of DNNs on processing pipelines, interoperability (as in system engineering) and end-to-end training for complex LT systems. I will outline potential benefits and end with a list of some of the currently open research questions.

Verónica Dahl
Computing Science Department, Simon Fraser University, Burnaby B.C., Canada

Verónica Dahl is an Argentine/Canadian computer scientist who is recognized as one of the 15 founders of the field of logic programming. She has contributed over 100 scientific publications in the fields of computational linguistics, deductive knowledge bases, computational molecular biology and web based virtual worlds. She has received numerous scientific awards, such as the Calouste Gulbenkian Award for Science and Technology, and a few literary awards as well. Her greatest ambition is to help bridge the gap between the formal and the humanistic sciences, in the hopes that this will be conducive to an overall more balanced world. She is presently Professor Emeritus at Simon Fraser University. Her research is supported by NSERC.
See here for full CV

Title:Truth and Beauty in Computational Linguistics

Abstract:
We coin and propose the "Colmerauer test" as an alternative to the Turing test as a method to evaluate computational linguistic theories along the axes of truth (how much of the truth are we able to glean within a given approach?) and beauty (how elegant are the formulations resulting from a given approach?). We argue that in computational linguistics, the Colmerauer test is superior to the more widely used Turing test.

Jan Wielemaker
Centrum voor Wiskunde en Informatica (CWI), the Netherlands
Kyndi, California

Jan Wielemaker is a Dutch computer scientist. He is the initiator of and lead developer of SWI-Prolog, the most widely used Prolog implementation. He has been involved in a large number of academic research projects in domains such as knowledge engineering, ontology management, natural language processing, linked data processing and data science as well as commercial activities including business rule enforcement, knowledge based systems, security and natural language understanding. The development of SWI-Prolog has been embedded and was guided by the needs of these projects, turning SWI-Prolog into a versatile, robust and scalable system. Current activities involve deploying Prolog for transparent data science and coordinating the developers community.

Title: A second life for Prolog

Abstract: Spread over three sessions we will first give a brief overview of the basics behind declarative programming and Prolog. In the next sessions we discuss how Prolog can be used as part of a modern IT tool chain. A tentative list of topics are (1) deploying Prolog as a web server including Pengines, Prolog engines on the web, (2) combining Prolog and R into a data science pipeline and (3) accessing linked data (RDF) from Prolog.

Alain Colmerauer (1941-2017), Pioneer of logic programming in natural language processing and LTC Program Committee member in 2005, left us on May 12, 2017

The list of conference topics includes the following (the ordering is not significative):

• communicative intelligence
• computational semantics
• computer modeling of language competence
• corpora-based methods in language engineering
• electronic language resources and tools
• formalization of natural languages
• HLT related policies
• HLT standards and best practices
• HLTs as support for e-learning
• HLTs as support for foreign language teaching
• HLTs as support in solving homeland security problems (technology applications and legal aspects)
• knowledge representation
• language-specific computational challenges for HLTs (especially for languages other than English)
• legal issues connected with HLTs (problems and challenges)
• less resourced languages
• logic programming in natural language processing
• man-machine NL interfaces
• methodological issues in HLT
• NL applications in robotics
• NL based interfaces
• NL understanding by computers
• NL user modeling
• NLP methods in cyber-criminality detection and prevention
• parsing and other forms of NL processing
• question answering
• sentiment, opinion and emotion analysis
• speech processing
• system prototype presentations
• systems with NL competence
• technological aspects of nonverbal linguistics
• text-based information retrieval and extraction
• tools and methodologies for developing multilingual systems
• translation enhancement tools
• validation in all areas of HLTs
• visionary papers in the field of HLT
• WordNet-like ontologies

This list is by no means closed and we are open to further proposals. Please do not hesitate to contact us in order to feed us with your suggestions and ideas of how to satisfy your expectations concerning the program. The Program Committee is also open to suggestions concerning accompanying events (workshops, exhibits, panels, etc). Suggestions, ideas and observations should be addressed directly to the LTC Co-Chairs by email (vetulani@amu.edu.pl or pap@limsi.fr) .

On numerous requests and questions we are pleased to announce a special call for demos and posters to be presented during the LTC 2017 (November 17-19, 2017) at dedicated time slots.

This Call for Demos and Posters Language is addressed to the whole concerned community: researchers, language engineers, language engineering providers. We welcome demos and/or posters presenting final results as well as current on-going projects concerning Language Resources (LR), LR Tools and LR-based Software, as well as related theoretical issues.
Companies are invited to present their novel or state-of-the-art products. We are interested in:

• language technology based products,
• application-scale language engineering tools,
• applications for production, conservation and maintenance of HLT language resources.

The content of demos/posters must be strictly compatible with the thematic scope of the LTC (see above).

SUBMISSION
Submission should be made in the same way as for LTC papers. Authors are supposed to submit an abstract of 300 – 500 words (including title, affiliation, keywords), no longer than one page.
Submission procedure as for regular LTC papers (with DEMO/POSTER in the paper description).

ACCEPTANCE/REJECTION
Submissions should not be anonymous and will be checked by Organizers for compatibility with the general LTC activity area, as well for formal correctness.

ABSTRACTS
Abstracts will be published in the “Abstracts Corner” of the proceedings:
- in both paper and electronic form if submitted before October 29 and the payment of the conference fee effected by November 1,
- in the electronic form only in case of submission before November 6 and payment before November 9 (Thursday).

TECHNICAL ASPECTS
Demo presenters are supposed to be equipped with necessary mobile computer equipment. No additional screens will be available. Internet will be provided. Posters must be in the A0 format and will be displayed horizontally. No other format will be accepted.

DATES/DEADLINES
Submission deadline: November 9

REGISTRATION AND FEES
All presenters must register to the LTC and pay the conference fee. Fees as well as the payment procedure are the same for demo, poster and paper presenters.
Presentation of demos and posters closely related to an accepted paper (the same title with the subtitle respectively DEMO or POSTER) is free for paper presenters.

CONTACT
ltc17@amu.edu.pl
mkubis@amu.edu.pl
vetulani@amu.edu.pl

The conference language is English.

Acceptance will be based on the reviewers' assessments (anonymous submission model /blind reviewing/). The accepted papers will be published in the conference proceedings (hard copy, with ISBN number) and on CD-ROM. The abstracts of the accepted contributions will also be made available via the conference page (during its lifetime). Publication requires full electronic registration and payment of the conference fee (full registration) by at least one of the co-authors. For the obvious reason that the conference fee must cover (in particular) the publication costs, the following rule is applied: "One registration fee entitles publication of one paper.

A post-conference volume with extended versions of selected papers will be published in the Springer Verlag series Lecture Notes in Artificial Intelligence.

The LTC 2005 post conference selection appeared in form of Special Issue of Archives of Control Sciences (2005, Volume 15 nb. 3 and Volume 15 nb. 4)

The LTC 2007 post-conference volume (revised, extended papers) appeared in the Springer Verlag series LNAI (vol. 5603).

The LTC 2009 post-conference volume (revised, extended papers) appeared in the Springer Verlag series LNAI (vol. 6562).

The LTC 2011 post-conference volume (revised, extended papers) appeared in the Springer Verlag series LNAI (vol. 8387).

The LTC 2013 post-conference volume (revised, extended papers) appeared in the Springer Verlag series LNAI (vol. 9561).

The LTC 2015 post-conference volume (revised, extended papers) is in preparation.

The conference accepts papers in English only. Papers (5 pages in the conference format) are due by September 25, 2017 (midnight, any time zone) and should not disclose the author(s) in any manner. In order to facilitate submission we have decided to reduce the formatting requirements as much as possible at this stage. Please, however, do observe the following:

1. Accepted fonts for texts are Times Roman, Times New Roman. Courier is recommended for program listings. Character size for the main text should be 10 points, with 11 points leading (line spacing).
2. Text should be presented in 2 columns, 8,42 cm each with 0,95 cm between columns (gutter).
3. The accepted document size is 5 pages formatted according to (1) and (2) above.
4. The paper must be submitted as a PDF document, together with an editable source in MS Word or Latex. (Please no other formats.)

The Word template (ELRA/LREC based format) is available here.

The Latex template (ELRA/LREC based format) is available here.

All submissions are to be made electronically via the LTC'17 web submission system (EasyChair).

Acceptance/refusal notification will be sent by October 16, 2017. At the same time, the detailed guidelines for the final submission of accepted papers will be published on the conference web site.

The deadline for final submissions is October 27, 2017.

Final papers should be sent by e-mail to ltc17@amu.edu.pl as an attachment and should conform to the following rules:

• The attached file should be named ltc-PAPERID-FirstAuthorName.pdf   /example: ltc-005-copernicus.pdf (the paper #5 with Copernicus as the submitting author).
• The subject of your e-mail should be LTC FINAL PAPER  PAPERID   /example: LTC FINAL PAPER 005.
• The required final format is the same as for the initial paper submission. Please use the same templates to prepare the final PDF file.

• Deadline for submission of papers for review: September 25, 2017
• Acceptance/Refusal notification: October 16, 2017
• Deadline for submission of final versions of accepted papers: October 23, October 27, 2017
• Conference: November 17-19, 2017
• LTC affiliated workshops and demo/poster sessions: see the sections corresponding to respective workshops and sessions

Non-student participants:

• Regular registration fee (payment before November 6, 2017): 200 EURO
• Late registration fee (payment after November 5, 2017): 260 EURO

• Regular registration fee (payment before November 6, 2017): 140 EURO
• Late registration fee (payment after November 5, 2017): 190 EURO

To be entitled to student rates the participant must present a student card (or equivalent document) valid on July 31, 2017.

Student registrations must be accompanied by proof of full-time student status (in form of scanned copy of a student ID card or equivalent document) and send by e-mail to ltc17@amu.edu.pl. The e-mail subject field must have the following format:
LTC-17-student-ID-card-'Name_of_participant'
(e.g. LTC-17-student-ID-card-Vetulani)

The conference fee covers:

• participation in the scientific program /including presentation of one paper/*)
• conference materials
• proceedings on CD and paper
• social events (banquet,...)
• coffee breaks

Conference fee for an accompanying persons is 50 EUR. The fee covers participation in non-scientific program (banquet,session coffee breaks).

The fee for one extra page (max. 2 allowed) will be charged 21 Euro.

*) In case of multiple submission the extra fee of 126 Euro for one additional paper of standard length (not covered by the conference fee paid by a co-author) is to be paid.

Day 1, Friday, November 17, 2017 Adam Mickiewicz University Library - 38/40 Ratajczaka Street 8:00 - 10:30 Registration Collegium Maius - 10 Fredry Street 11:00 - 11:15 Opening by the Adam Mickiewicz University Rector 11:15 - 11:40 Colette Colmerauer: about Alain Colmerauer's work PDF 11:40 - 12:20 Truth and Beauty in Computational Linguistics - Invited Talk by Verónica Dahl PDF 12:20 - 14:10 Lunch break Adam Mickiewicz University Library - 38/40 Ratajczaka Street 14:10 - 15:30 Sentiment Analysis Information Retrieval/Information Extraction 1 Morphology 15:30 - 16:00 Coffee break 16:00 - 16:40 Addressing the Language Resource Gap through Alternative Incentives, Workforces and Workflows - Invited Talk by Chris Cieri PDF 16:45 - 18:25 Emotions, Decisions, Opinions Workshop (EDO)   Alain Colmerauer Special Session Day 2, Saturday, November 18, 2017 University Library 8:20 - 9:40 Language Resources and Tools 1 Information retrival/Information extraction 2 Computational semantics 1 9:40 - 10:40 POSTERS/DEMOS session & coffee 10:40 - 11:20 A Second Life for Prolog - Invited Talk by Jan Wielemaker PDF 11:25 - 12:25 Text annotation/normalization Applications Machine Translation 12:30 - 13:30 Presentation by the LTC sponsor: The Amazon Development Center 13:30 - 15:15 Lunch break 15:15 - 15:55 The Impact of Neural Networks on Language Technologies a Case Study on Machine Translation - Invited Talk by Joseph van Genabith PDF 15:55 - 16:25 Coffee break 16:25 - 17:45 Language Resources and Tools 2 LRL Workshop 1 Speech 1 17:50 - 19:10 A Second Life for Prolog Tutorial (1) - by Jan Wielemaker LRL Workshop 2 Text Analysis 20:30 - 00:00 Conference Gala Dinner Day 3, Sunday, November 19, 2017 University Library 08:00 - 10:00 Second Life for Prolog Tutorial (2) - by Jan Wielemaker PolEval Workshop 1 Computational semantics 2 10:00 - 10:30 Coffee break 10:30 - 11:45 Presentation by the LTC sponsor: Samsung Poland R&D Institute PDF 11:45 - 12:45 Panel discussion 12:45 - 14:15 Lunch break 14:15 - 15:35 Language Resources and Tools 3 PolEval Workshop 2 Speech 2 15:40 - 16:00 Closure session TECHNICAL SESSIONS Day 1: November 17, 2017 Session: Sentiment Analysis 14:10 - 15:30 A Book Reviews Dataset for Aspect Based Sentiment Analysis PDF Tamara Álvarez-López, Milagros Fernández-Gavilanes, Enrique Costa-Montenegro, Jonathan Juncal-Martínez, Silvia García-Méndez and Patrice Bellot Lack of consensus among sentiment analysis tools: A suitability study for SME firms PDF Aidan Connelly, Victor Kuri and Marco Palomino Sentiment Analysis of Customer Feedback in the Business Domain PDF Omar El-Begawy, Robin Wikström and Hannu Toivonen Opinion Holder and Object Extraction in Sentiment Analysis of Russian Texts PDF Arina Reshetnikova Session: Information Retrieval/Information Extraction 1 14:10 - 15:30 Language Independent Named Entity Recognition using Distant Supervision PDF Julia Dembowski, Michael Wiegand and Dietrich Klakow Combining Profiles and Local Information for Named Entity Classification: Adjustment of a Domain and Language Independent Approach PDF Isabel Moreno, María Teresa Romá-Ferri and Paloma Moreda Automatic Taxonomy Generation: A Use-Case in the Legal Domain PDF Cécile Robin, James O‘Neill and Paul Buitelaar Title Categorization based on Category Granularity PDF Kazuya Shimura and Fumiyo Fukumoto Session: Morphology 14:10 - 15:30 A holistic approach at a morphological inflection task PDF Rashel Fam and Yves Lepage Out-of-Vocabulary Word Probability Estimation using RNN Language Model PDF Irina Illina and Dominique Fohr Automatic Pairing of Perfective and Imperfective Verbs in Polish PDF Zbigniew Kaleta Session: Emotions, Decisions, Opinions Workshop (EDO) 16:45 - 18:25 Introduction Michal Ptaszynski, Rafal Rzepka and Pawel Dybala Can one emoticon say a thousand words?: Automatic estimation of meaning ambiguity of emoticons based on linguistic expressibility PDF Naoto Ishii, Fumito Masui and Michal Ptaszynski On the contribution of specific entity detection and comparative construction to automatic spin detection in biomedical scientific publications PDF Anna Koroleva and Patrick Paroubek Three attempts in PolEval 2017 Sentiment Analysis Task PDF Michal Ptaszynski, Fumito Masui, Arkadiusz Janz, Jan Kocoń, Maciej Piasecki, Monika Zaśko-Zielińska and Pawel Dybala Suppressed Negative-Emotion-Detecting Method by using Transitions in Facial Expressions and Acoustic Features PDF Joji Uemura, Kazuya Mera, Yoshiaki Kurosawa and Toshiyuki Takezawa Long distance history influences sentence valence in narrative texts PDF Liam Watson, Barry Devereux and Brian Murphy Workshop Summary and Conclusions Michal Ptaszynski, Rafal Rzepka and Pawel Dybala Alain Colmerauer Special Session 16:45 - 18:25 Logic Programming and Lean Reasoning Systems PDF Adam Meissner Knowledge and Software Engineering with Prolog PDF Grzegorz J Nalepa, Szymon Bobek, Mateusz Ślażyński and Krzysztof Kutt CLP(FD)-based Information Systems in Space Management Optimization PDF Irene Rodrigues, Daniel Diaz and Salvador Abreu Prolog for Expert Knowledge Using Domain-Specific and Controlled Natural Languages PDF Dietmar Seipel, Falco Nogatz and Salvador Abreu Day 2: November 18, 2017 Session: Language Resources and Tools 1 8:20 - 9:40 (Temporal) Language Models as a Competitive Challenge PDF Filip Graliński Mosaic n-grams: Avoiding combinatorial explosion in corpus pattern mining for agglutinative languages PDF Balázs Indig Processing historical texts with contemporary NLP tools PDF Krzysztof Jassem and Paweł Skórzewski Anotatornia 2 – an annotation tool geared towards historical corpora PDF Marcin Woliński, Witold Kieraś and Dorota Komosińska Session:Information Retrieval/Information Extraction 2 8:20 - 9:40 Hybrid Deep Open-Domain Question Answering PDF Ahmad Aghaebrahimian Sentence Answer Selection for Open Domain Question Answering via Deep Word Matching PDF Fabrizio Ghigi, Diana Turcsany, Thomas Kaltenbrunner and Maurizio Cibelli The New Clothes for an Old Cookbook PDF Cvetana Krstev, Duško Vitaš, Miloš Utvić Identification of Domain-Specific Senses based on Word Embedding Learning PDF Attaporn Wangpoonsarp and Fumiyo Fukumoto Session: Computational Semantics 1 8:20 - 9:40 Quora Duplicate Query Elimination PDF Efe Arin, Ugur Gudelek and Murat Ozbayoglu plWordNet as a Basis for Large Emotive Lexicons of Polish PDF Arkadiusz Janz, Jan Kocoń, Maciej Piasecki and Monika Zaśko-Zielińska Interpreting Syntactic Relations in Attributive Groups PDF Julia Romaniuk, Nina Suszczanska and Przemyslaw Szmal Syntactic-Semantic Classes of Context-Sensitive Synonyms Based on a Bilingual Corpus PDF Zdenka Uresova, Eva Fučíková, Eva Hajicova and Jan Hajic POSTERS/DEMOS Session 9:40 - 10:40 Detection of new words and their senses in Twitter data using Wikipedia PDF Apichai Chan-Udom, Karman Chan and Yoshimi Suzuki Creating a Norwegian valence corpus from a deep grammar DEMO PDF Lars Hellan, Dorothee Beermann, Tore Bruland, Tormod Haugland and Elias Aamot Can word embeddings be used in application of morphosyntactic disambiguation task? PDF Adrianna Janik Axio Speech Corpus: design, structure, and preliminary analyses PDF Katarzyna Klessa and Bożena Niećko-Bukowska plWordNet 3.0 emo and WordNetLoom editor PDF Maciej Piasecki, Agnieszka Dziob, Monika Zaśko-Zielińska, Tomasz Naskręt and Ewa Rudnicka RICeSTQUTranslate: A suggestion oriented machine translation system for English-Persian cross-lingual information retrieval in medical domain PDF Amin Rahmani, Mohammad Reza Falahati and Mohammd Bagher Dastgheib Opinion Holder & Object Extraction in Sentiment Analysis of Russian Texts DEMO PDF Arina Reshetnikova German evaluative adjectives. Semi-automatic analysis of hotel reviews PDF Janusz Taborek and Michał Pasternak The Adventure with Prolog at Adam Mickiewicz University in Poznań – Selected Examples PDF Zygmunt Vetulani, Jacek Martinek and Marek Kubis A New Tool for Quality Control of Text Corpora PDF Zygmunt Vetulani, Marta Witkowska and Umut Canbolat Processing, Analysing and Visualising Language Data using solutions prepared in CLARIN-PL LTC PDF Tomasz Walkowiak, Marcin Pol and Maciej Piasecki Improving adverse drug reaction detection with models combination PDF Magdalena Wiercioch Translating competency questions to simple SPARQL-OWL PDF Dawid Wiśniewski, Jędrzej Potoniec and Agnieszka Ławrynowicz Question Classification via Deep Neural Networks PDF Tugba Yildiz, Savas Yildirim and Ozge Samli Beyond Neural MT PDF Andrzej Zydroń Calculating the Percentage Reduction in Translator Effort when using Machine Translation PDF Andrzej Zydroń and Qun Liu Session: Text Annotation/Normalization 11:25 - 12:25 Determining Multi Word Aspects by Using Apriori Algorithm and Syntactic Rules for Turkish Hotel Reviews PDF Ekin Ekinci, Hazal Turkmen and Sevinç Ilhan Omurca Pros and Cons of Normalizing Text with Thrax PDF Krzysztof Jassem, Filip Graliński and Tomasz Obrębski Using Transfer Learning in Part-Of-Speech Tagging of English Tweets PDF Sara Meftah, Nasredine Semmar, Othman Zennaki and Fatiha Sadat Session: Applications 11:25 - 12:25 PADI-web: Platform for Automated Extraction of Animal Disease Information from the Web PDF Elena Arsevska, Sylvain Falala, Jocelyn de Goër de Hervé, Renaud Lancelot, Julien Rabatel and Mathieu Roche Creation of a Dialogue Corpus for Automatic Analysis of Phonetic Convergence PDF Jolanta Bachan, Mariusz Owsianny and Grażyna Demenko Multi-Conditionally Trained ASR System for Reverberant Speech Captured by Spherical Microphone Array in Adverse Acoustic Conditions PDF Peter Viszlay, Ján Staš, Martin Lojka, Jozef Greššák, Jozef Juhár and Slavomír Gereg Session: Machine Translation 11:25 - 12:25 Effects of Pre- and Post-Processing on Persian to English SMT PDF Davood Mohammadifar and Gholamreza Ghassem Sani An Empirical Study for a Machine Aided Translation of French Prepositions ’a’, ’de’ and ’en’ into English PDF Violaine Prince Towards a direct Japanese-Polish machine translation system PDF Patrycja Świeczkowska Session: Language Resources and Tools 2 16:25 - 17:45 Towards Automatic Detection of Correct Domain Words in OCR Texts from Polish Digital Libraries PDF Filip Graliński, Rafał Jaworski and Piotr Wierzchoń How to Improve Optical Character Recognition of Historical Finnish Newspapers Using Open Source Tesseract OCR Engine PDF Mika Koistinen, Kimmo Kettunen and Jukka Kervinen Review of Techniques for Extraction of Bilingual Lexicon from Comparable Corpora PDF Manpreet Singh Lehal, Dr. Ajit Kumar and Dr. Vishal Goyal Processing, Analysing and Visualising Language Data using solutions prepared in CLARIN-PL LTC PDF Marcin Pol, Tomasz Walkowiak and Maciej Piasecki Session: Speech 1 16:25 - 17:45 Creation and evaluation of MaryTTS speech synthesis for Polish PDF Jolanta Bachan and Marceli Tokarski Statistical modelling of speech units in HMM-based speech synthesis for Arabic PDF Amal Houidhek, Vincent Colotte, Zied Mnasri, Denis Jouvet and Imene Zangar The structure of Polish nasalized vowels: results based on spatial energy distribution and formant frequency analysis PDF Anita Lorenc, Katarzyna Klessa and Daniel Król LRL Workshop 1 16:25 - 17:45 Corpus base linguistic exploration via forced alignments with a ‘light-weight’ ASR tool PDF Jamison Cooper-Leavitt, Lori Lamel, Annie Rialland, Martine Adda-Decker and Gilles Adda Improving Tokenization, Transcription Normalization and Part-of-speech Tagging of Ainu Language through Merging Multiple Dictionaries PDF Karol Nowakowski, Michal Ptaszynski and Fumito Masui Using LT tools in classroom and coding club activities to help LRLs PDF Delyth Prys, Dewi Bryn Jones and Stefano Ghazzali On the development of NLP tools for the Georgian language PDF Irakli Tsikarishvili, Krzysztof Jassem, Ioseb Otskheli and Urszula Boryczka LRL Workshop 2 16:25 - 17:45 Toward educating and motivating the crowd - a crowdsourcing platform for harvesting the fruits of NLP students’ labour PDF Rafal Jaworski, Sanja Seljan and Ivan Dunder A neural network architecture for low-resource machine transliteration PDF Ngoc Tan Le and Fatiha Sadat Automatic converb detection in early Braj PDF Rafal Jaworski and Krzysztof Stroński Session: Text Analysis 17:50 - 19:10 Syntactic Sentence Simplification and Sentence Compression for German PDF Lena Schiffer, Uwe Quasthoff and Lydia Müller Exctracting Editor’s opinions from Newspaper Editorial PDF Yoshimi Suzuki and Fumiyo Fukumoto Analysing Positional Language Models for Natural Language Generation PDF Marta Vicente and Elena Lloret Day 3: November 19, 2017 PolEval Workshop 1 08:00 - 10:00 Results of the PolEval 2017 Competition: Part-of-Speech Tagging Shared Task PDF Łukasz Kobyliński and Maciej Ogrodniczuk Morphosyntactic disambiguation for Polish with bi-LSTM neural networks PDF Katarzyna Krasnowska-Kieraś Evaluating an averaged perceptron morphosyntactic tagger for Polish PDF Piotr Pęzik and Sebastian Laskowski MorphoDiTa-based Tagger Addapted to the Polish Language Technology PDF Maciej Piasecki and Wiktor Walentynowicz Character-Based Neural POS Tagger PDF Paweł Rychlikowski, Michał Zapotoczny and Jan Chorowski KRNNT: Polish Recurrent Neural Network Tagger PDF Krzysztof Wróbel PolEval Workshop 2 14:15 - 15:35 Fine-tuning Tree-LSTM for phrase-level sentiment classification on a Polish dependency treebank. Submission to PolEval task 2 PDF Tomasz Korbak and Paulina Żak A Sequential Child-Combination Tree-LSTM Network for Sentiment Analysis PDF Michał Lew and Piotr Pęzik Polish Language Sentiment Analysis with Tree-Structured Long Short-Term Memory Network PDF Norbert Ryciak Results of the PolEval 2017 Competition: Sentiment Analysis Shared Task PDF Aleksander Wawer and Maciej Ogrodniczuk Computational Semantics 2 08:00 - 10:00 Shared forest representation of predicate-argument structures for shared syntactic forests PDF Tomasz Bartosiak Open semantic analysis: The case of word level semantics in Danish PDF Finn Arup Nielsen and Lars Kai Hansen Towards the evaluation of feature embedding models of the fusional languages PDF Alina Wróblewska, Katarzyna Krasnowska-Kieraś and Piotr Rybak Session: Language Resources and Tools 3 14:15 - 15:35 Creating a Norwegian valence corpus from a deep grammar PDF Lars Hellan, Dorothee Beermann, Tore Bruland, Tormod Haugland and Elias Aamot Personal names spell-checking – a study related to Uzbek PDF Jasur Isroilov and Tomasz Jastrząb Building a Lemmatizer and a Spell-checker for Sorani Kurdish PDF Shahin Salavati and Sina Ahmadi Session: Speech 2 14:15 - 15:35 Developing Resources for Automated Speech Processing of the African Language Naija (Nigerian Pidgin) PDF Brigitte Bigi, Bernard Caron and Oyelere S. Abiola Acoustic study of Tone and Lexical Stress Interaction in Punjabi PDF Swaran Lata, Raghu Arora and Bhavna Thakur Speech Emotion Classification of African Tone Languages PDF Umoh M. Nnamso, Chukwudi Nwokoro, Samuel B. Oyong, Pius Ejodamen, Susan L. Asuquo, Etim E. Ekong and Moses E. Ekpenyong

EDO Workshop paper submission deadline : September 25, 2017.
Acceptance/rejection notification: October 10, 2017.
Final version submission deadline (camera ready): October 23, 2017.
Conference/Workshop dates: November 17-19, 2017 (half-day, afternoon)

Inscription procedure: as for the general LTC (+ cc to workshop chairs)

Fees: The EDO Workshop is an integral part of the LTC (with autonomous Program Committee). Fees and payment procedures are the same as for LTC and cover participation in the general program. Free for participants registered to the general LTC. Single registration covers only one paper presentation (cf. the Publication Policy section).

Presentation: publication in the LTC proceedings (paper + CD)

More about EDO 2017: cf. http://arakilab.media.eng.hokudai.ac.jp/LTC8/EDO2017/ABOUT.html (the access to the program of both the main conference and the workshop (as well as the social program) is the same for all LTC/EDO participants).

Chairs
• Girish Nath Jha (JNU, India)
• Claudia Soria (CNR-ILC, Italy)


Papers submission deadline : September 25, 2017.
Workshop dates: November 17-19, 2017.
Deadline for submission of camera-ready final versions of the accepted papers: October 23, 2017.
See also the 5th LRL website.

The rapid growth of language technology has created a new challenge for many languages of the world today. While for some, this can take the shape of a positive competition among the stake holders, for others it can push them further down in the race towards endangerment and extinction. The LT-LRL Workshop is an attempt to bring together all stake holders, users, developers, researchers, language activists, policy makers on a single platform and discuss how resources, policies, standards could be developed for these languages so that they can develop technologies to enable themselves in the digital age. We will particularly welcome contributions addressing the following issues:

1) LRL: charting the field - what do we know about currently available LTs for LRLs? What is the current status of language technologies and use of LRLs in the digital and social media environments? How to draw a comprehensive and accurate picture and create a road map for future? Who are the actors to be involved? What is the experience of researchers and developers?

2) LRL: Resource development - how are the LRLs dealing with resource crunch, creation and related issues of standards, IDEs and platforms, funding, usability, sharing etc? What are the perceptions and roles of various stake holders including the governments, industry and language communities? What are the additional challenges posed by multilingual societies? What are the language preservation strategies for LRLs in the digital age?

3) LRL : technology development - challenges in the development of specific enabling technologies for LRLs at language, speech and multi-modal levels. How are these technologies used in areas such as communication, education, entertainment, health, administration. governance etc?

Fees: LRL is an integral part of the LTC (with autonomous Program Committee). Fees and payment procedures are the same for general LTC and worshop participants (cover participation in the general LTC program). Notice: the workshop is free for participants registered to the general LTC. Single registration covers only one paper presentation (general LTC or workshops) (cf. the Publication Policy section in case of more than one submitted paper).

Submition:
See the LRL web site: the 5th LRL website.

Reviewing and acceptance: on the ground of blind reviewing

More LRL participation details: cf. also the general program (the access to the program of both the main conference and the workshop (as well as the social program) is the same for all LTC/LRL participants).

PolEval Organizing Committee

Maciej Ogrodniczuk (Institute of Computer Science, Polish Academy of Sciences)
Łukasz Kobyliński (Institute of Computer Science, Polish Academy of Sciences / Sages)
Aleksander Wawer (Institute of Computer Science, Polish Academy of Sciences)

Theme and Motivation

PolEval is a SemEval-inspired evaluation campaign for natural language processing tools for Polish. Submitted tools compete against one another within certain tasks selected by organisers, using available data and are evaluated according to pre-established procedures. PolEval 2017-related papers will be presented at a special session during LTC 2017.

Task 1: POS Tagging

There is an ongoing discussion whether the problem of part of speech tagging is already solved, at least for English, by reaching the tagging error rates similar or lower than the human inter-annotator agreement, which is ca. 97%. In the case of languages with rich morphology, such as Polish, there is however no doubt that the accuracies of around 91% delivered by taggers leave much to be desired and more work is needed to proclaim this task as solved. The aim of this proposed task is therefore to stimulate research in potentially new approaches to the problem of POS tagging of Polish, which will allow to close the gap between the tagging accuracy of systems available for English and languages with rich morphology.

Registered systems compete in three settings:

Subtask (A): Morphosyntactic disambiguation and guessing: Given a sequence of segments, each with a set of possible morphosyntactic interpretations, the goal of the task is to select the correct interpretation for each of the segments and provide an interpretation for segments for which only 'ign' interpretation has been given (segments unknown to the morphosyntactic dictionary).
Subtask (B): Lemmatisation: Given a sequence of segments, each with a set of possible morphosyntactic interpretations, the goal of the task is to select the correct lemma for each of the segments and provide a lemma for segments for which only 'ign' interpretation has been given (segments unknown to the morphosyntactic dictionary).
Complete system (C): POS tagging: Given a raw text in Polish, the goal of the task is to segment the text by separating individual flexemes and provide the correct lemma and POS tag for each of the segments.

Task 2: Sentiment analysis

Sentiment analysis is a vital research area, approached at different levels: phrase-level (either in the context of opinion targets/aspects or phrases defined as syntactic sub-trees), sentence-level (related to the task of tweet-level analysis). The aim of this task is to promote research on this topic in the context of the Polish language, provide reference data sets to work and motivation for potentially new methods.

The systems compete in one setting: Given a set of syntactic dependency trees, the goal of the task is to provide the correct sentiment for each sub-tree (phrase). Phrases correspond to sub-trees of dependency parse tree. The annotations assign sentiment values to whole phrases (and in some cases, sentences), regardless of their type.

Important Dates

September 25, 2017: Deadline for submission of papers for review
October 16, 2017: Acceptance/Refusal notification
October 23, 2017: Deadline for submission of final versions of accepted papers
November 17-19, 2017: Conference

Presentation of results

All accepted system descriptions, following the LTC 2017-compatible review process (in a special track and with a special deadline set to end of August) will be published in the conference proceedings provided the author registers to the conference under standard LTC conditions. Extended versions of best papers from each main track will be recommended for publication in the post-conference Springer's LNAI volume (subject to additional rounds of reviews).

LTC 2017 is located in the Adam Mickiewicz University Library (Biblioteka Uniwersytecka), ul. Ratajczaka 38/40, 61-816 Poznań.

Conference opening session on Nov. 17, 11 a.m. will take place in Collegium Maius (ul. Fredry 10, 7 min. walk from the conference location).

Registration desk will be set in the University Library (opening on Nov. 17, 8 am).

Collegium Maius, Opening Session ul. Fredry 10 Adam Mickiewicz University Library, Conference place ul. Ratajczaka 38/40
(click the map to see better) How to get from the University Liberary to Collegium Maius? AWARDS FOR THE BEST STUDENT PAPERS As at the 2nd, 3rd, 4th, 5th, 6th and 7th Language and Technology Conferences (2005, 2007, 2009, 2011, 2013,2015) special awards will be granted to the best student papers. The regular or PhD students (on the date of paper submission) are concerned. Co-authored papers will be considered provided that the students' contributions exceeds 60% and that the main author(s) is (are) student(s)(this fact must be documented by a written declaration signed by all co-authors). In 2005 the Jury, composed of the Program Committee members participating in the conference, awarded this distinction to: Ronny Melz (University of Leipzig), Hartwig Holzapfel (University of Karlsruhe), Marcin Woliński (IPI PAN, Warsaw) (picture at LTC 2011). In 2007 the award for the best student paper was granted to Darja Fišer (University of Ljubljana). In 2009 two awards were granted: to Mahmoud EL-Haj (University of Essex, UK) (left) and Alexander Pak (LIMSI-CNRS, Orsay, France) (right). In 2011 the Jury decided to award three student contributions: Narayan Choudhary (Jawaharlal Nehru University, New Delhi, India)(left), Moses Ekpenyong (University of Uyo, Nigeria)(middle) and Marek Kubis (Adam Mickiewicz University in Poznań, Poland) (right). In 2013 the Jury decided to award: Dominika Rogozińska, IPI PAN Warszawa, Juan Luo (left picture), Waseda University, Japan, and Matea Srebačić (right picture), University of Zagreb, Croatia. In 2015 the Jury decided to award: Keith Lia (left picture), University of Copenhagen, Denmark, Marzieh Razavi (middle picture), Idiap Research Institute, Martigny, Switzerland, and Zijian Győző Yang (right picture), Pázmány Péter Catholic University, Hungary. Notice. Pictures are clickable.

This site is in progress. Further important practical information will be published shortly. Please consult this site again from time to time.

Students interested in joining our team of volunteers at the conference are kindly asked to send an email to obrebski@amu.edu.pl (cc: mkubis@amu.edu.pl). Please use LTC2017-Volunteer as a subject of your message.